Survey: Machine Learning in Production Rendering

TL;DR

This survey reviews recent advances in machine learning techniques applied to production rendering, highlighting improvements in image quality and efficiency across various challenging light transport scenarios.

Contribution

It provides a comprehensive overview of how deep learning methods are transforming rendering processes in animation, covering fundamental principles and recent practical applications.

Findings

Deep neural networks improve image quality in rendering.

ML approaches reduce computational overhead.

Techniques are actively evolving with promising results.

Abstract

In the past few years, machine learning-based approaches have had some great success for rendering animated feature films. This survey summarizes several of the most dramatic improvements in using deep neural networks over traditional rendering methods, such as better image quality and lower computational overhead. More specifically, this survey covers the fundamental principles of machine learning and its applications, such as denoising, path guiding, rendering participating media, and other notoriously difficult light transport situations. Some of these techniques have already been used in the latest released animations while others are still in the continuing development by researchers in both academia and movie studios. Although learning-based rendering methods still have some open issues, they have already demonstrated promising performance in multiple parts of the rendering pipeline, and people are continuously making new attempts.